© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13052
    Prev
    Next
    INDEX
    Explanations

    the letters "PL" followed sometimes by other letters or other times by numbers

    oai_token-act-pair · gemini-2.0-flash

    Names/Codes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    セ
    -0.46
    <-
    -0.46
     mon
    -0.44
    ルク
    -0.42
     gol
    -0.42
    Way
    -0.42
    idor
    -0.42
     <-
    -0.41
     Mol
    -0.41
     Way
    -0.41
    POSITIVE LOGITS
     lenker
    0.97
     <<<<<<<<<<<<<<
    0.82
    MemoryWarning
    0.79
    oredCriteria
    0.72
     للاسماء
    0.71
    GEBURTSDATUM
    0.70
    AutoScaleMode
    0.68
     estekak
    0.68
     المعيارى
    0.68
    Personensuche
    0.67
    Activations Density 0.512%

    No Known Activations